{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:55:11Z","timestamp":1743105311973,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781124"},{"type":"electronic","value":"9783031781131"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78113-1_30","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:01:59Z","timestamp":1733245319000},"page":"459-471","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CroMA: Cross-Modal Attention for\u00a0Visual Question Answering in\u00a0Robotic Surgery"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8331-5257","authenticated-orcid":false,"given":"Greetta","family":"Antonio","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2493-897X","authenticated-orcid":false,"given":"Jobin","family":"Jose","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0886-9478","authenticated-orcid":false,"given":"Sudhish","family":"N George","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9489-5161","authenticated-orcid":false,"given":"Kiran","family":"Raja","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Seenivasan, L., Islam, M., Krishna, A.K., Ren, H.: Surgical-VQA: visual question answering in surgical scenes using transformer. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 33\u201343. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-16449-1_4"},{"issue":"1","key":"30_CR2","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s42492-024-00160-z","volume":"7","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Fan, W., Peng, P., Yang, X., Zhou, D., Wei, X.: Dual modality prompt learning for visual question-grounded answering in robotic surgery. Vis. Comput. Ind. Biomed. Art 7(1), 9 (2024)","journal-title":"Vis. Comput. Ind. Biomed. Art"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Spasic, I., Nenadic, G.: Clinical text data in machine learning: systematic review. JMIR Med. Inf. 8(3) (2020)","DOI":"10.2196\/17984"},{"issue":"1","key":"30_CR4","doi-asserted-by":"publisher","first-page":"19826","DOI":"10.1038\/s41598-021-98390-1","volume":"11","author":"D Sharma","year":"2021","unstructured":"Sharma, D., Purushotham, S., Reddy, C.K.: MedFuseNet: an attention-based multimodal deep learning model for visual question answering in the medical domain. Sci. Rep. 11(1), 19826 (2021)","journal-title":"Sci. Rep."},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Sharma, H., Jalal, A.S.: Image captioning improved visual question answering. Multimedia Tool Appl. 81(24), 34775\u201334796 (2022)","DOI":"10.1007\/s11042-021-11276-2"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Bai, L., Islam, M., Seenivasan, L., Ren, H.: Surgical-VQLA: transformer with gated vision-language embedding for visual question localized-answering in robotic surgery. arXiv preprint arXiv:2305.11692 (2023)","DOI":"10.1109\/ICRA48891.2023.10160403"},{"key":"30_CR7","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"30_CR8","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 32\u201342 (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"30_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"30_CR11","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"issue":"2","key":"30_CR12","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.P.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"30_CR15","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: SimVLM: simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Islam, M., Seenivasan, L., Ming, L.C., Ren, H.: Learning and reasoning with the graph structure representation in robotic surgery. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III, 23, pp. 627\u2013636. Springer (2020)","DOI":"10.1007\/978-3-030-59716-0_60"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"30_CR21","unstructured":"Allan, M., et al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)"},{"key":"30_CR22","unstructured":"Allan, M., et al.: 2017 robotic instrument segmentation challenge. arXiv preprint arXiv:1902.06426 (2019)"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6281\u20136290 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"30_CR24","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers and distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Cord, M., Thome, N.: MUTAN: multimodal tucker fusion for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2612\u20132620 (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Xiang, S., Chen, Q., Fang, X., Guo, M.: Improving visual question answering by multimodal gate fusion network. In: 2023 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2023)","DOI":"10.1109\/IJCNN54540.2023.10191453"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Thome, N., Cord, M.: BLOCK: Bilinear superdiagonal fusion for visual question answering and visual relationship detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 1, pp. 8102\u20138109 (2019)","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Praveen, R.G., et al.: A joint cross-attention model for audio-visual fusion in dimensional emotion recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2486\u20132495 (2022)","DOI":"10.1109\/CVPRW56347.2022.00278"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Georgescu, M.I., et al.: Multimodal multi-head convolutional attention with various kernel sizes for medical image super-resolution. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2195\u20132205 (2023)","DOI":"10.1109\/WACV56688.2023.00223"},{"key":"30_CR30","doi-asserted-by":"crossref","unstructured":"Wu, Z., Liu, L., Zhang, Y., Mao, M., Lin, L., Li, G.: Multimodal crowd counting with mutual attention transformers. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2022)","DOI":"10.1109\/ICME52920.2022.9859777"},{"key":"30_CR31","unstructured":"Arevalo, J., Solorio, T., Montes-y-G\u00f3mez, M., Gonz\u00e1lez, F.A.: Gated multimodal units for information fusion. arXiv preprint arXiv:1702.01992 (2017)"},{"key":"30_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Xiao, B., et al.: Florence-2: advancing a unified representation for a variety of vision tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4818\u20134829 (2024)","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"30_CR35","unstructured":"Li, J., et al.: LLaVA-Surg: towards multimodal surgical assistant via structured surgical video learning. arXiv preprint arXiv:2408.07981 (2024)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78113-1_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:07:54Z","timestamp":1733245674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78113-1_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031781124","9783031781131"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78113-1_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}